© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 12913
    Prev
    Next
    INDEX
    Explanations

    This can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canonical
    -0.16
    canonical
    -0.15
    Canonical
    -0.15
     canonical
    -0.14
     canned
    -0.13
     canon
    -0.12
     Canterbury
    -0.12
     Canal
    -0.11
     cannon
    -0.11
     Cannon
    -0.11
    POSITIVE LOGITS
     can
    0.54
    åı¯ä»¥
    0.47
     можно
    0.40
     dapat
    0.40
     można
    0.37
    ï¼Įåı¯ä»¥
    0.36
     можна
    0.34
    can
    0.33
     lze
    0.32
     ÙĬÙħÙĥÙĨ
    0.30
    Activations Density 0.267%

    No Known Activations